What If the Input is Expanded in OOD Detection?
This work addresses the reliability of machine learning models in open-world deployments by enhancing OOD detection, representing an incremental improvement through a novel scoring approach.
The paper tackles the problem of out-of-distribution (OOD) detection by expanding input representations through common corruptions, revealing a confidence mutation phenomenon where OOD data confidence decreases under corruptions while in-distribution data remains stable, and proposes the CoVer scoring method that improves separability, achieving state-of-the-art results on benchmarks like CIFAR-10 and ImageNet.
Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits its representation dimension. In this work, we introduce a novel perspective, i.e., employing different common corruptions on the input space, to expand that. We reveal an interesting phenomenon termed confidence mutation, where the confidence of OOD data can decrease significantly under the corruptions, while the ID data shows a higher confidence expectation considering the resistance of semantic features. Based on that, we formalize a new scoring method, namely, Confidence aVerage (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different corrupted inputs and the original ones, making the OOD and ID distributions more separable in detection tasks. Extensive experiments and analyses have been conducted to understand and verify the effectiveness of CoVer. The code is publicly available at: https://github.com/tmlr-group/CoVer.